# How Cat Wu actually uses coding agents

Claude Code product, Anthropic

**If you take one thing:** `Fresh config per model`, reset at every model launch. she tests each new model on a clean slate instead of carrying old tweaks forward.

- **Agent:** Claude Code (app) ([source, 2026-03-19](https://claude.com/blog/product-management-on-the-ai-exponential))
- **Agent:** Claude Tag ([source, 2026-07-21](https://simonwillison.net/2026/Jul/21/cat-and-thariq/))
- **Model:** Claude Opus 5.5 ([source, 2026-09-22](https://x.com/_catwu/status/2102437713781944397))
- **Model:** Claude Fable 5.1 ([source, 2026-09-22](https://x.com/_catwu/status/2102443572205437435))
- **Review:** Claude code review clears the outer layers; code owners review the core ([source, 2026-07-21](https://simonwillison.net/2026/Jul/21/cat-and-thariq/))
- **Harness:** Auto mode; tasks kicked off from mobile into cloud sessions ([source, 2026-07-21](https://simonwillison.net/2026/Jul/21/cat-and-thariq/))
- **Skills:** PR commit ([source, 2025-10-29](https://every.to/podcast/transcript-how-to-use-claude-code-like-the-people-who-built-it))
- **Hooks:** permission approval hooks ([source, 2026-02-12](https://x.com/_catwu/status/2021848561638625556))

## In their words

> Claude Code is where I build prototypes, evals, and scripts, many of which call Claude API. I use this when the output is code.

> Maybe I say, “Hey, I think we should implement this new feature in Cowork,” and I’ll tag in Claude Tag to do a first pass at it.

> I’ve been using Opus 5.5 as a daily driver and love its clear communication skills and ability to write in my style.

> I still turn to Fable 5.1 for my "fire and forget" coding tasks.

> But increasingly, for the changes at the outer layers, we actually have Claude code review fully review those.


Archetype (our label): Purist. Newest source: 2026-09-23.
Card: https://www.prehistoriq.com/stacks/catherinewu/ · Data: https://github.com/prehistoriq/stacks/blob/main/data/stacks/catherinewu.json